New Preprint: Latent disconnectome prediction of long-term cognitive symptoms in stroke
Updated: Oct 25, 2021
Web app coming soon: Disconnectome Symptoms Discoverer (DSD)
What is the paper about:
Stroke significantly impacts quality of life. However, the long-term cognitive evolution in stroke is poorly predictable at the individual level. There is an urgent need for a better prediction of long-term symptoms based on acute clinical neuroimaging data.
Previous works have demonstrated a relationship between the location of white matter disconnections and clinical symptoms. However, rendering the entire space of possible lesion-deficit associations optimally surveyable will allow for a systematic association between brain disconnections and cognitive-behavioural measures at the individual level.
we exploit nonlinear dimensionality reduction to report the characteristics of disconnection patterns of more than 1000 stroke lesions in a two-dimensional summary morphospace. Acute disconnectomes drawn from an independent distribution were projected into the morphospace to predict neuropsychological scores 1 year after stroke. Linking the latent disonnectome morphospace to neuropsychological outcomes yields a comprehensive atlas of disconnectome- deficit relations across 86 neuropsychological scores. Out-of-sample prediction derived from this atlas achieved average accuracy over 80%.
Our novel predictive framework is available as an interactive web application, the disconnectome symptoms discoverer (DSD), to provide the foundations for a new approach to modelling cognition in stroke.
#stroke#disconnectome#umap#django#workinprogress#webapp coming soon
👇👇 Curious? Keep on reading right here 👇👇
Preprint available: https://researchgate.net/publication/355184021_Latent_disconnectome_prediction_of_long-term_cognitive_symptoms_in_stroke
Talk available soon